© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20677
    Prev
    Next
    INDEX
    Explanations

    finding something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åįĪ
    -0.10
    ç§ijæķĻ
    -0.10
    带ç»Ļ
    -0.09
    鸾
    -0.09
    ç¦Ģ
    -0.08
    æĵħ
    -0.08
    é¢Ħ
    -0.08
    inois
    -0.08
    çĤ¹åĩ»æŁ¥çľĭ
    -0.08
    ç¥Ŀ
    -0.08
    POSITIVE LOGITS
    诸
    0.10
    éĢŀ
    0.10
    羣åĪĩ
    0.10
    åı£æ°Ķ
    0.09
     rh
    0.09
    çķ´
    0.09
    æŁ
    0.09
    Rh
    0.08
     Fraser
    0.08
    -fi
    0.08
    Activations Density 0.087%

    No Known Activations